{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:OUJTRZ46BABSK5O5S2JI2C2T55","short_pith_number":"pith:OUJTRZ46","schema_version":"1.0","canonical_sha256":"751338e79e08032575dd96928d0b53ef53562cd0b22c176c1835c83851fdc360","source":{"kind":"arxiv","id":"2103.04475","version":1},"attestation_state":"computed","paper":{"title":"LogBERT: Log Anomaly Detection via BERT","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Haixuan Guo, Shuhan Yuan, Xintao Wu","submitted_at":"2021-03-07T22:56:01Z","abstract_excerpt":"Detecting anomalous events in online computer systems is crucial to protect the systems from malicious attacks or malfunctions. System logs, which record detailed information of computational events, are widely used for system status analysis. In this paper, we propose LogBERT, a self-supervised framework for log anomaly detection based on Bidirectional Encoder Representations from Transformers (BERT). LogBERT learns the patterns of normal log sequences by two novel self-supervised training tasks and is able to detect anomalies where the underlying patterns deviate from normal log sequences. T"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2103.04475","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2021-03-07T22:56:01Z","cross_cats_sorted":[],"title_canon_sha256":"c293e82b4e9c332c470fa842e6e32d0025ca4703a258c03dc582700db4d3a9b4","abstract_canon_sha256":"0a5cd724982716ddc6adf49d85cbc46182a0339fcc0aca2098fe99927092f80e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:21:05.943718Z","signature_b64":"fw9LeICedIpW8almOyHUllg6Li8yPAfJi5dLDTvrq5+j3LhKsEJARAuzaV56sXs+3mWLQ8brm3HjoJTHfub8Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"751338e79e08032575dd96928d0b53ef53562cd0b22c176c1835c83851fdc360","last_reissued_at":"2026-07-05T02:21:05.943329Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:21:05.943329Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LogBERT: Log Anomaly Detection via BERT","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Haixuan Guo, Shuhan Yuan, Xintao Wu","submitted_at":"2021-03-07T22:56:01Z","abstract_excerpt":"Detecting anomalous events in online computer systems is crucial to protect the systems from malicious attacks or malfunctions. System logs, which record detailed information of computational events, are widely used for system status analysis. In this paper, we propose LogBERT, a self-supervised framework for log anomaly detection based on Bidirectional Encoder Representations from Transformers (BERT). LogBERT learns the patterns of normal log sequences by two novel self-supervised training tasks and is able to detect anomalies where the underlying patterns deviate from normal log sequences. T"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.04475","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2103.04475/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2103.04475","created_at":"2026-07-05T02:21:05.943386+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.04475v1","created_at":"2026-07-05T02:21:05.943386+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.04475","created_at":"2026-07-05T02:21:05.943386+00:00"},{"alias_kind":"pith_short_12","alias_value":"OUJTRZ46BABS","created_at":"2026-07-05T02:21:05.943386+00:00"},{"alias_kind":"pith_short_16","alias_value":"OUJTRZ46BABSK5O5","created_at":"2026-07-05T02:21:05.943386+00:00"},{"alias_kind":"pith_short_8","alias_value":"OUJTRZ46","created_at":"2026-07-05T02:21:05.943386+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21900","citing_title":"Continuous Behavioral Authentication via Multi-Expert BERT Log Analysis for Secure Data Sharing","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10988","citing_title":"Seeing the Needle in the Haystack: Towards Weakly-Supervised Log Instance Anomaly Localization via Counterfactual Perturbation","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OUJTRZ46BABSK5O5S2JI2C2T55","json":"https://pith.science/pith/OUJTRZ46BABSK5O5S2JI2C2T55.json","graph_json":"https://pith.science/api/pith-number/OUJTRZ46BABSK5O5S2JI2C2T55/graph.json","events_json":"https://pith.science/api/pith-number/OUJTRZ46BABSK5O5S2JI2C2T55/events.json","paper":"https://pith.science/paper/OUJTRZ46"},"agent_actions":{"view_html":"https://pith.science/pith/OUJTRZ46BABSK5O5S2JI2C2T55","download_json":"https://pith.science/pith/OUJTRZ46BABSK5O5S2JI2C2T55.json","view_paper":"https://pith.science/paper/OUJTRZ46","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.04475&json=true","fetch_graph":"https://pith.science/api/pith-number/OUJTRZ46BABSK5O5S2JI2C2T55/graph.json","fetch_events":"https://pith.science/api/pith-number/OUJTRZ46BABSK5O5S2JI2C2T55/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OUJTRZ46BABSK5O5S2JI2C2T55/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OUJTRZ46BABSK5O5S2JI2C2T55/action/storage_attestation","attest_author":"https://pith.science/pith/OUJTRZ46BABSK5O5S2JI2C2T55/action/author_attestation","sign_citation":"https://pith.science/pith/OUJTRZ46BABSK5O5S2JI2C2T55/action/citation_signature","submit_replication":"https://pith.science/pith/OUJTRZ46BABSK5O5S2JI2C2T55/action/replication_record"}},"created_at":"2026-07-05T02:21:05.943386+00:00","updated_at":"2026-07-05T02:21:05.943386+00:00"}